Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag a destructive, non-idempotent, open-world write, but the description adds real operational context beyond them: writes are never retried automatically, credit use requires approval, invalid canvases return 400 VALIDATION_ERROR before saving, and HTML is parsed and sanitized without running a browser. That tells the agent both how failures surface and that a retry is unsafe.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose then constraints, and nearly every sentence carries actionable rules. The main inefficiency is that the long canvas/HTML-rules passage appears twice in the schema (html_front and html_back) and again in the description, so a portion of the text is redundant rather than value-adding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive nested-object write with no output schema, the description covers validation, publishing and approval well. It does not say what a successful call returns (design ID, draft status) or how the design must later be attached to a campaign, which an agent needs to chain the next step.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema coverage, the description does meaningful work: it explains the pixel canvas per size option, the inline-style-only constraint, the 2 MB per-side cap, and that auto_publish degrades to a draft unless both sides carry validated HTML. Still missing is any meaning for theme, layout, include_street_view or orientation beyond what their short schema strings say.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence pairs a specific verb with the resource ('Create a mail design') and immediately distinguishes the two creation modes: custom HTML versus a saved prompt draft. An agent can tell this is the create endpoint rather than the update path (dealmachine_patch_mail_designs_id) without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the conditions that select each mode ('Custom HTML', 'or save a prompt as a draft'), that publishing requires complete validated front and back HTML, and that prompt-only designs cannot be auto-published. It also sets a hard prerequisite of user approval and confirmed=true. It stops short of naming sibling alternatives such as patch_mail_designs_id for edits.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.